Feng He
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes a comprehensive framework for LLM-based agent unlearning, enabling agents to selectively forget specific knowledge (states, trajectories, or environments) while maintaining performance and resisting knowledge inference by adversaries.
The paper proposes ADAM, a novel and highly effective privacy attack that systematically extracts sensitive data from LLM agent memory by adaptively querying the victim agent's memory based on data distribution and entropy.
Papers
ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying
Xingyu Lyu, Jianfeng He, Ning Wang, Yidan Hu +4 more
The paper proposes ADAM, a novel and highly effective privacy attack that systematically extracts sensitive data from LLM agent memory by adaptively querying the victim agent's memory based on data di…